mlsanityData to 14 Oct 2026

NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning

arXiv 2111.13984 ↗First posted 27 Nov 2021cs.LG cs.CV cs.MScited by 5

Not on the map. Why?

Abstract (arXiv)

Optimizing nonconvex (NCVX) problems, especially nonsmooth and constrained ones, is an essential part of machine learning. However, it can be hard to reliably solve such problems without optimization expertise. Existing general-purpose NCVX optimization packages are powerful but typically cannot handle nonsmoothness. GRANSO is among the first optimization solvers targeting general nonsmooth NCVX problems with nonsmooth constraints, but, as it is implemented in MATLAB and requires the user to provide analytical gradients, GRANSO is often not a convenient choice in machine learning (especially deep learning) applications. To greatly lower the technical barrier, we introduce a new software package called NCVX, whose initial release contains the solver PyGRANSO, a PyTorch-enabled port of GRANSO incorporating auto-differentiation, GPU acceleration, tensor input, and support for new QP solvers. NCVX is built on freely available and widely used open-source frameworks, and as a highlight, can solve general constrained deep learning problems, the first of its kind. NCVX is available at https://ncvx.org, with detailed documentation and numerous examples from machine learning and other fields.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 27 Nov 2021.

Builds on

16 of 35 references.

References · 16

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 641
  4. 2014Identifying and attacking the saddle point problem in high-dimensional non-convex optimizationcited by 289
  5. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 161
  6. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  7. 2020Geoopt: Riemannian Optimization in PyTorchcited by 114
  8. 2013Manopt, a Matlab toolbox for optimization on manifoldscited by 113
  9. 2016Pymanopt: A Python Toolbox for Optimization on Manifolds using Automatic Differentiationcited by 94
  10. 2018geomstats: a Python Package for Riemannian Geometry in Machine Learningcited by 71
  11. 2019Optimization for deep learning: theory and algorithmscited by 70
  12. 2015MLlib: Machine Learning in Apache Sparkcited by 55
4 more
  1. 2018Subgradient Descent Learns Orthogonal Dictionariescited by 17
  2. 2018McTorch, a manifold optimization library for deep learningcited by 16
  3. 2019GENO -- GENeric Optimization for Classical Machine Learningcited by 12
  4. 2021The ensmallen library for flexible numerical optimizationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 2; 2026: 1.

5 papers.

  1. 2025SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinationscited by 9
  2. 2023Interaction-Aware Trajectory Planning for Autonomous Vehicles with Analytic Integration of Neural Networks into Model Predictive Controlcited by 5
  3. 2022Optimization for Robustness Evaluation beyond ℓp Metricscited by 3
  4. 2026REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinationscited by 1
  5. 2025PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networkscited by 0